svenbl80/roberta-base-finetuned-new-mnli-run-0

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0242
• Validation Loss: 0.7506
• Train Accuracy: 0.8638
• Epoch: 9

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 245430, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.4535	0.4013	0.8557	0
0.3264	0.3638	0.8641	1
0.2447	0.4053	0.8649	2
0.1799	0.4217	0.8683	3
0.1305	0.4702	0.8621	4
0.0937	0.5705	0.8624	5
0.0664	0.6041	0.8616	6
0.0480	0.6936	0.8627	7
0.0342	0.7156	0.8624	8
0.0242	0.7506	0.8638	9

Framework versions

• Transformers 4.28.0
• TensorFlow 2.9.1
• Datasets 2.15.0
• Tokenizers 0.13.3